Investigating unsupervised learning for text categorization bootstrapping Export

@inproceedings{citeulike:3811420, abstract = {We propose a generalized bootstrapping algorithm in which categories are described by relevant seed features. Our method introduces two unsupervised steps that improve the initial categorization step of the bootstrapping scheme: (i) using Latent Semantic space to obtain a generalized similarity measure between instances and features, and (ii) the Gaussian Mixture algorithm, to obtain uniform classification probabilities for unlabeled examples. The algorithm was evaluated on two Text Categorization tasks and obtained state-of-the-art performance using only the category names as initial seeds.}, address = {Morristown, NJ, USA}, author = {Gliozzo, Alfio and Strapparava, Carlo and Dagan, Ido}, booktitle = {HLT '05: Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing}, citeulike-article-id = {3811420}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1220575.1220592}, citeulike-linkout-1 = {http://dx.doi.org/10.3115/1220575.1220592}, doi = {10.3115/1220575.1220592}, keywords = {bootstrapping, categorization, learning, text, unsupervised}, location = {Vancouver, British Columbia, Canada}, pages = {129--136}, posted-at = {2008-12-19 16:20:34}, priority = {2}, publisher = {Association for Computational Linguistics}, title = {Investigating unsupervised learning for text categorization bootstrapping}, url = {http://dx.doi.org/10.3115/1220575.1220592}, year = {2005} }

TY - CONF ID - citeulike:3811420 L3 - citeulike-article-id:3811420 N2 - We propose a generalized bootstrapping algorithm in which categories are described by relevant seed features. Our method introduces two unsupervised steps that improve the initial categorization step of the bootstrapping scheme: (i) using Latent Semantic space to obtain a generalized similarity measure between instances and features, and (ii) the Gaussian Mixture algorithm, to obtain uniform classification probabilities for unlabeled examples. The algorithm was evaluated on two Text Categorization tasks and obtained state-of-the-art performance using only the category names as initial seeds. CY - Vancouver, British Columbia, Canada AD - Morristown, NJ, USA EP - 136 TI - Investigating unsupervised learning for text categorization bootstrapping PB - Association for Computational Linguistics T2 - HLT '05: Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing SP - 129 KW - bootstrapping KW - categorization KW - learning KW - text KW - unsupervised AU - Gliozzo, Alfio AU - Strapparava, Carlo AU - Dagan, Ido PY - 2005/// UR - http://dx.doi.org/10.3115/1220575.1220592 ER -